Grounded QA fixture corpora — Fenwake documents for the Managed RAG ranking
A fictional document corpus used to evaluate managed RAG systems.
What this resource provides or represents
This resource provides the benchmark documents used to test whether a managed RAG system can ingest, retrieve, ground answers, cite sources, and stay in sync with source changes. It represents the corpus a tool must read, rather than any knowledge the model already has. The set includes a fixed main corpus for ordinary evaluation and a separate mutable corpus for freshness checks.
Scope and composition
The boundaries of the resource and how its meaningful parts are organized for evaluation.
Benchmark fixture corpus for Managed RAG / RAG-as-a-Service evaluations.
A fixed main document set for ingestion, retrieval, grounded generation, and citations, plus a separate mutable set for freshness testing.
All content is fictional, so systems must answer from the documents themselves.
Versions
Public context for the resource versions used in evaluation.
Version 1
Initial corpus release for the Managed RAG ranking, with a fixed main set and a separate mutable sync set.
Benchmarks that use this resource
A resource has global identity and may be reused across benchmarks.
Managed RAG
Uses Version 1.
→